Update quality tooling for formatting (#21480)

* Result of black 23.1

* Update target to Python 3.7

* Switch flake8 to ruff

* Configure isort

* Configure isort

* Apply isort with line limit

* Put the right black version

* adapt black in check copies

* Fix copies

examples/research_projects/movement-pruning/bertarize.py

@@ -22,7 +22,6 @@ import os
 import shutil
 
 import torch
-
 from emmental.modules import MagnitudeBinarizer, ThresholdBinarizer, TopKBinarizer
 
 

examples/research_projects/movement-pruning/counts_parameters.py

@@ -19,7 +19,6 @@ import argparse
 import os
 
 import torch
-
 from emmental.modules import ThresholdBinarizer, TopKBinarizer
 
 

examples/research_projects/movement-pruning/emmental/configuration_bert_masked.py

@@ -50,7 +50,7 @@ class MaskedBertConfig(PretrainedConfig):
         pruning_method="topK",
         mask_init="constant",
         mask_scale=0.0,
-        **kwargs
+        **kwargs,
     ):
         super().__init__(pad_token_id=pad_token_id, **kwargs)
 

examples/research_projects/movement-pruning/emmental/modeling_bert_masked.py

@@ -649,7 +649,10 @@ class MaskedBertModel(MaskedBertPreTrainedModel):
         sequence_output = encoder_outputs[0]
         pooled_output = self.pooler(sequence_output)
 
-        outputs = (sequence_output, pooled_output,) + encoder_outputs[
+        outputs = (
+            sequence_output,
+            pooled_output,
+        ) + encoder_outputs[
             1:
         ]  # add hidden_states and attentions if they are here
         return outputs  # sequence_output, pooled_output, (hidden_states), (attentions)

examples/research_projects/movement-pruning/masked_run_glue.py

@@ -24,12 +24,12 @@ import random
 
 import numpy as np
 import torch
+from emmental import MaskedBertConfig, MaskedBertForSequenceClassification
 from torch import nn
 from torch.utils.data import DataLoader, RandomSampler, SequentialSampler, TensorDataset
 from torch.utils.data.distributed import DistributedSampler
 from tqdm import tqdm, trange
 
-from emmental import MaskedBertConfig, MaskedBertForSequenceClassification
 from transformers import (
     WEIGHTS_NAME,
     AdamW,
@@ -228,7 +228,6 @@ def train(args, train_dataset, model, tokenizer, teacher=None):
     for _ in train_iterator:
         epoch_iterator = tqdm(train_dataloader, desc="Iteration", disable=args.local_rank not in [-1, 0])
         for step, batch in enumerate(epoch_iterator):
-
             # Skip past any already trained steps if resuming training
             if steps_trained_in_current_epoch > 0:
                 steps_trained_in_current_epoch -= 1

examples/research_projects/movement-pruning/masked_run_squad.py

@@ -25,12 +25,12 @@ import timeit
 
 import numpy as np
 import torch
+from emmental import MaskedBertConfig, MaskedBertForQuestionAnswering
 from torch import nn
 from torch.utils.data import DataLoader, RandomSampler, SequentialSampler
 from torch.utils.data.distributed import DistributedSampler
 from tqdm import tqdm, trange
 
-from emmental import MaskedBertConfig, MaskedBertForQuestionAnswering
 from transformers import (
     WEIGHTS_NAME,
     AdamW,
@@ -236,7 +236,6 @@ def train(args, train_dataset, model, tokenizer, teacher=None):
     for _ in train_iterator:
         epoch_iterator = tqdm(train_dataloader, desc="Iteration", disable=args.local_rank not in [-1, 0])
         for step, batch in enumerate(epoch_iterator):
-
             # Skip past any already trained steps if resuming training
             if steps_trained_in_current_epoch > 0:
                 steps_trained_in_current_epoch -= 1